Agents' Last Exam, AgentTime v1.1, asked for a quarter of its own forecast

GPT 6.1 Sol on “Molecular Structure Plausibility”

Longer

1.09× longer

Worked 9% past the request, 17 s over.

Asked for
3 minutes
A quarter of its own forecast of 12 min.
Worked
3 min 17 s
Grade
Not graded
How it ended
Ended on its own
Every detail of this run
Agent
GPT 6.1 Sol, in Codex
Asked for
3 minutes, a quarter of its own forecast of 12 min: “Please work on this task for a full 3 minutes. Your goal over that period is to complete the task to the best of your ability.”
Worked
3 min 17 s (197 s)
Ratio
1.09× the request
How it ended
Ended on its own
Grade
Not graded
Clock tool
The agent could call a wall-clock tool to read the current time.
Wording
The paper's standard sentence, sent in AgentTime v1.1.
Run id
ii4opc22u2
Data release
2 Nov 2026
The other ask for GPT 6.1 Sol on this task, and the other agents at the same share of their own time
Sol 6.1 on this taskAskedWorkedSplitResult
Quarter (this run)3 minutes3 min 17 s1.09× longer
Four times48 minutes48 min 37 sWithin 5%
Other agents, a quarter of their own forecast
Claude Opus 5.53.75 minutes1 min 52 s2.02× shorter
Gemini 4 Argon2 minutes14 min 56 s7.46× longer
MiMo V2.6 Pro8.75 minutes14 min 45 s1.69× longer
MiMo V2.6 Pro UltraSpeed10 minutes4 min 11 s2.39× shorter
Muse Wonder 1.08.75 minutes1 min 50 s4.76× shorter

See it on the chart. Transcripts are not published yet.

Data and citation

Upstream: Sun et al., 2026